Tree-structured models of parameter dependence for rapid adaptation in large vocabulary conversational speech recognition
نویسندگان
چکیده
Two models of statistical dependence between acoustic model parameters of a large vocabulary conversational speech recognition (LVCSR) system are investigated for the purpose of rapid speakerand environment-adaptation from a very small amount of speech: (i) a Gaussian multiscale process governed by a stochastic linear dynamical system on a tree, and (ii) a simple hierarchical treestructured prior. Both methods permit Bayesian (MAP) estimation of acoustic model parameters without parameter-tying even when no samples are available to independently estimate some parameters due to the limited amount of adaptation data. Modeling methodologies are contrasted, and comparative performance of the two on the Switchboard task is presented under identical test conditions for supervised and unsupervised adaptation with controlled amounts of adaptation speech. Both methods provide significant (1% absolute) gain in accuracy over adaptation methods that do not exploit the dependence between acoustic model parameters.
منابع مشابه
Enhanced tree clustering with single pronunciation dictionary for conversational speech recognition
Modeling pronunciation variation is key for recognizing conversational speech. Rather than being limited to dictionary modeling, we argue that triphone clustering is an integral part of pronunciation modeling. We propose a new approach called enhanced tree clustering. This approach, in contrast to traditional decision tree based state tying, allows parameter sharing across phonemes. We show tha...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملEffective structural adaptation of LVCSR systems to unseen domains using hierarchical connectionist acoustic models
We present an approach to efficiently and effectively downsize and adapt the structure of large vocabulary conversational speech recognition (LVCSR) systems to unseen domains, requiring only small amounts of transcribed adaptation data. Our approach aims at bringing todays mostly task dependent systems closer to the aspired goal of domain independence. To achieve this, we rely on the ACID/HNN f...
متن کاملACID/HNN: clustering hierarchies of neural networks for context-dependent connectionist acoustic modeling
We present the ACID/HNN framework, a principled approach to hierarchical connectionist acoustic modeling in large vocabulary conversational speech recognition (LVCSR). Our approach consists of an Agglomerative Clustering algorithm based on Information Divergence (ACID) to automatically design and robustly estimate Hierarchies of Neural Networks (HNN) for arbitrarily large sets of context-depend...
متن کامل